[Lex Computer & Tech Group/LCTG] Prompt Engineering
Ted Kochanski
tedpkphd at gmail.com
Sat Aug 31 15:11:18 PDT 2024
All,
This one is of personal interest
My father-in-law suffered from ALS for the last couple of years of his life
[back about 40 years ago]
It was particularly hard on him since he was a Generalist Physician who had
seem some ALS patients in his career
The positive feature of his illness was that his wife [my mother-in-law]
was a nurse and could manage his care at home with just some assistance
As his illness progressed from initial problems walking to problems talking
-- the two of them developed a private code involving him blinking his eyes
to communicate -- based on binary logic chains for common issues
While he eventually lost the ability to even mouth words -- He never lost
his mental capacities nor the ability to blink
They agreed that when he stopped breathing that there would be no
resuscitation -- that's how it finally ended
I'm always hopeful that there will be some useful means of communicating
using tech long before there is a "cure"
Ted
On Fri, Aug 30, 2024 at 1:56 PM Robert Primak via LCTG <lctg at lists.toku.us>
wrote:
> These results are well within the realm of what I alluded to in previous
> messages. Notes:
>
> (1) This LLM was trained on just one patient, which increases the
> likelihood of accuracy. It does not provide general applicability to
> different individuals. (At least not yet.)
>
> (2) The signals used came from very specific locations within the
> subject's brain, and these locations were known to (and adjusted by) the
> researchers. For this type of application, such methods are perfectly
> acceptable. Notice that implanted electrodes are a much finer instrument
> than scanned EEG or f-MRI signals. Also, this research was not attempting
> to read "thoughts", but rather to interpret signals which would normally
> trigger muscle movements to produce the elements of human speech. Very
> different concepts!
>
> (3) I am impressed with how rigorously the researchers have reported what
> their LLM was doing with the data it was processing.This makes these
> results entirely plausible.
>
> (4) I do hope this research leads to more widely applicable LLM and AI
> models for use on more patients with limited or no speech capabilities.
> Including communication with people born without these faculties. This type
> of research will provide real benefits to individuals, caregivers, health
> care teams and families, as well to our society in general.
>
> I hope this research and projects like it will receive the funding they
> need to move forward. This is a very promising area of research and medical
> device development. I do not see this particular kind of research as
> threatening to "read people's minds" or interfere with privacy or freedoms.
> That's not what this research is intended to do, and I don't see how it
> could lead to such outcomes.
>
> -- Bob Primak
>
>
> On Friday, August 30, 2024 at 01:22:35 PM EDT, <comahony at yahoo.com>
> wrote:
>
>
> Related to this conversation, earlier today I read the following account
> of advancing the state of the art in another email…
>
>
> A Lost Voice Regained
>
> A man who lost the ability to speak four years ago is sounding like his
> earlier self, thanks to a collection of brain implants and machine learning
> models.
>
> What’s new: Researchers built a system that decodes speech signals from
> the brain
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxm43qgyTW7lCdLW6lZ3npW5sGV9k3bZR2DN2V-pqL6NpqjW3gL-0Z3MqF9DW46KrSy23_yvhW4Zt_645d18f0W2BZ1lP8l6ggxW6HTgPc96Kw1rW4BP3zr6qcH_ZW6SyHP799_n7pW24-DQN60LkKGW3chlcS6gg9f8W4pvYtq7MF24zVdtdDP6-bcwRN7dfzXw4T4JdW8f_c9m1hbBymW279syz1145Z7W7tdxxS6k7xRLW7_Mc7c21j7-4W30qvCy6lYzQwN5TBwH7Whx9qN5JkqKvJK_zZW9jZP2l1Gb0nbW6v2RD17w-2sdW3sqY-l77N43ff5zPMYH04> of
> a man who lost the ability to speak clearly due to amyotrophic lateral
> sclerosis, also known as ALS, and enables him to speak through a synthetic
> version of his former voice. At the start of the study, his efforts to
> speak were intelligible only to his personal caregiver. Now he converses
> regularly with family and friends, The New York Times reported
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxmn3qgyTW7Y8-PT6lZ3kxW2M87d95Yb6wNN1LDVKdJS3bTVKbc3P8VzXXMMZ--HQwMdBDVt_QvH1qkyCQW91LzXp8GJb31W3wQ5wh7S0rz6W7kmh8T3308pGW2CVzzt5cFxgjF2Jpk9vczqsW8MhtCF1njm9JW8x6MGq26sylPN4DlhWgvFmH9N3vyv8kz11rKW5-rH-r4gYgHJW2c62Gj532yPcW1npm-41hd_qGW47f29t3q3WjwW6shSqB7fwS96W2K-Cf72CfR8sN1pTLt_p8WhLW2CtQ7z4xghkBMy5wZWqR0bfW3F9yGH74rsSGW1_lvjL5TXmGHW5G3v4k1vnsGJf5mZFwT04>.
> Nicholas Card built the system with colleagues University of
> California-Davis, Stanford University, Washington University, Brown
> University, VA Providence Healthcare, and Harvard Medical School.
>
> How it works: The authors surgically implanted four electrode arrays into
> areas of the brain that are responsible for speech. The system learned to
> decode the patient’s brain signals, decide the most likely phonemes he
> intended to speak, determine the words those phonemes express, and display
> and speak the words aloud using a personalized speech synthesizer.
>
> - After the patient recovered from the implantation surgery, the
> authors collected data for training and evaluating the system. They
> recorded his brain signals while he tried to speak during 84 sessions, each
> between 5 and 30 minutes, over 32 weeks. The sessions were split into two
> tasks: copying, in which the patient spoke sentences shown on a screen, and
> conversation, in which he spoke about whatever he wanted. Initial sessions
> focused on copying. Later, when the authors had accrued paired brain
> signals and known sentences, they focused on conversation.
> - A gated recurrent unit
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxlP3qgyTW6N1vHY6lZ3q2W7--0Kx3VD509W4ndtLc6B9xqyN1vwhTLPQ4sWW453yj-3q5cY4W4wf-G84cZMMhW4PC80C9kw_zTW4tSKJ655c7qmW70cTT19dBxvkW7X7w4t68gm-QW8bg9Qq3vR1tgW6QCtd959nRL_W9gJ0q_3HPCmvW4ncl5N1p7SGqW22KNL96svczCMXzN9D44byZMfSg7JzlqnvW2FJC0L1-_RyrW8JqrPw8wwlJYN44Djq9JSb8kW35Zqct18wc8gV6BwJz8PG38kW22WKGY3kg0kQf9dZ3CR04> (GRU)
> learned to translate brain signals into a sequence of phonemes. The authors
> trained the model after each session on all recordings made during that
> session. To adapt it to day-to-day changes in brain activity, they also
> fine-tuned it during later sessions: After they recorded a new sentence,
> they fine-tuned the GRU on a 60/40 mix of sentences from the current
> session and previous sessions.
> - A weighted finite-state transducer (WFST), based on a pretrained
> 5-gram language model and described in the supplementary information
> here
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxm43qgyTW7lCdLW6lZ3pPW2KdCtd1cZnZBVZcp0y8wRx9GW3CfRZH4xtV2sVyD8dK1Qv2dlW7qVhQm63Q38_W6WFy3T4v_znnW20_-LZ6wYsz3M62QVtR0-GnVPrSd97hF3XWW3R2Yhb99mg5kW36G9Z27Vd9wrW3WSG055hCQ5WW8ZW87-6CSD5DW3tT0y21LzYcjW8RPtYj2TKcGrW35Lnqk2LMFNTW4nlfVG7gvkSmN12N86fSKHX4W3hfTZ06c9TX5W7QdNqy3ZGPx8N7tsTKcZqGN-W8k0Kg76HRfWLW7DR7sh9525ccW1qWYl-4gmPNCf204KK404>),
> translated sequences of phonemes into sentences. Given a sequence, it
> generated the 100 most likely sentences.
> - Given the likely sentences, the authors ranked them according to the
> probability that the GRU, WFST, and OPT
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxlP3qgyTW6N1vHY6lZ3pvW89nKCv1QQfdVW7Nh93q1TzRDmW8Fb_Fx8Y19L3W6q78Yd2WsrWPVLb6MH6jRfDqW7zQ5cJ1JgpMTW6LzfYL34NXg1N7QN7bQFRzC5W3D7qh04FP118Vt5fHY308kzqV_Glh21GSx5rW55swqg61_WhvW3mLvgV3LHLlBW6_8FRF69yFF9V3hnwT4xcmY1W5jQ-M818_4BFW1H22l_98xmfDW5Gdr7B2cT8XsN57f8rPDJ20hW1m6js-1tvPxbW3LQBpr7Yz3x-W48J7cr297Tz0f7F3T-804>,
> a pretrained large language model, would generate them.
> - A pretrained StyleTTS 2
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxlP3qgyTW6N1vHY6lZ3n-W8xZNlK5yWGYTN1nhjBPVpBBdW8HL3Mv4CjWCZW6TQ9Jp5tSM32W3Q6FdL3-Fr4hW8bsTcF2h2hQjW256wgp79x0fyW2fGSBx8_HlBfW8f3p2H29MqBYW12fBqD8g-K1gVkBv9123992fW4ZWylB11JRclW8PS69N2GlxLjN4GsG81c4nYBW6NqQ9n2Bj-mbW8bZV-p7cjyXkDL0-S9B7qGW8p4rfp3jqLqZN27_--7jJHs_W2TTXyp8zC3ztTGnlt1L_t5MW5s2VW63fWBk-f2vP5Nq04> text-to-speech
> model turned the highest-ranking sentence into speech. The authors
> fine-tuned the model on recordings of the patient’s voice from before the
> onset of his illness, such as podcasts.
>
> Results: After two hours of recording the patient’s brain signals and
> training on that data, the system achieved 90.2 percent accuracy in the
> copying task. By the final session, the system achieved 97.5 percent
> accuracy and enabled the patient to speak on average 31.6 words per minute
> using a vocabulary of 125,000 words.
>
> Behind the news: Previous work either had much lower accuracy
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxmn3qgyTW7Y8-PT6lZ3mBN7YpgFTDKcCNW8wn50859qZwbW18NBhJ2k4m00TLFh72SSTK5W1fM0wH52q0kkW5-PSwz70k-_JW10_qm-3sSQtDW7mSW7N5fJ5tLW1NSZyb8gZbFWW5gRF0G9lbZ3WMN_nJQXvn3hN8yjzmz5WJt8VgrhBY2wNNn7W1SRrG-7DJF6MW6lfYM05fcVnWW1yvF3S4X5lnVN4KyNCDLLHzPW8bM1Qb54t_H7W7yBgMS1g8qr-W3QhVGp7q5pT6W4tw6535mN772N49jryhTN-jzW6Kw0tv50kXp9W3b5CDq6ssQ1vW32ndyJ2qmb--W2XNDg94gPlhBf3thnQ604> or
> generated a limited vocabulary
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxmn3qgyTW7Y8-PT6lZ3lZW4x5BXj4kn76fW9118F_9b6BRdW5MSfwd9dr0LzW5WGlkS2YYHGPW9hSlWx7szMvrW2fnl_z8409QvN1KvQYzCmnCKW3qNZzm3Vnht8W6tKpcj8YpCC8W6dp-6855RryJW1l3Kd45KpdkFW5ffVfm1PNnMxN5KXXtVrCSQrW81JMq_3KS-D8W3LdZF91YCyycW814GxB71SxTPW95zFFS6zVpNkW8YD3V47dVTByW8sq6Ns71SPtyN80QKtLnCWFHN5yhLQfQf-1LW6J02mX4VPzQ5W4C6lC-3ztT3QW3CFD0w6KWb1GW2Z2FnQ9l6_QCW3vXq394nJzfCf3RzGM-04>.
> The new work improved upon a 2023 study
> <https://info.deeplearning.ai/e3t/Ctc/LX+113/cJhC404/VVsmGC4pHCpMW8G19Lw2f28pLW46ZLVZ5kht08MtGxm43qgyTW7lCdLW6lZ3lmW6bFChs11QMFbW9hWf2f6lF9gDW18q9-C7y3B0nW1n-Tqn4Y1ZGcW77DMz42DC6mxW8my3B78-bqq7W2Z6dZX5dVwgZW6kMh4j3379gQW1nr0_L185lbbW7Gk0wv1Y0ZWsW8t48sV117xptN69hP9YX1P_TW3g0r4J4jNXKqW3s7kdD48J9B_W6wXqQ784LyQHW5X8NJT76vySmN53Gytpdq6vqW4K4J_y8BG5GdW6hMYBQ5B54y-W3lDz3b4WCVQ0W5M317-7npSSXW7N-Rn36VMJ3jW1Cl7fH1YTtTlV4M8724THXjYdkGV_z04> that
> enabled ALS patients to speak with 76.2 percent accuracy using a vocabulary
> of equal size.
>
> Why it matters: Relative to the 2023 study on which this one was based,
> the authors changed the positions of the electrodes in the brain and
> continued to update the GRU throughout the recording/training sessions.
> It’s unclear which changes contributed most to the improved outcome. As
> language models improve, new models potentially could act as drop-in
> replacements for the models in the authors’ system, further improving
> accuracy. Likewise, improvements in speech-to-text systems could increase
> the similarity between the synthetic voice and the patient’s former voice.
>
> -Conor
>
>
> On Aug 28, 2024, at 1:03 AM, Robert Primak via LCTG <lctg at lists.toku.us>
> wrote:
>
>
> So the question in my mind is whether this research, to the extent
> discussed, is valid
>
> Yes, that is the question. And this question awaits someone else trying to
> confirm the results. But with both the programming and the training methods
> cloaked in "black box" secrecy, there are important considerations which no
> one will ever be allowed to investigate. Anyway, that's the way this sort
> of research is usually handled.
>
> -- Bob Primak
>
>
> On Tuesday, August 27, 2024 at 06:42:40 PM EDT, John P. Rudy <
> jjrudy1 at comcast.net> wrote:
>
>
> But if there is a specific disabled person and something directly related
> to that person works to 50% that would be fantastic. So the question in my
> mind is whether this research, to the extent discussed, is valid
>
>
>
> *From:* Robert Primak <bobprimak at yahoo.com>
> *Sent:* Tuesday, August 27, 2024 6:29 PM
> *To:* 'Harry Forsdick' <harry at forsdick.com>; John P. Rudy <
> jjrudy1 at comcast.net>
> *Cc:* lctg at lists.toku.us
> *Subject:* Re: [Lex Computer & Tech Group/LCTG] Prompt Engineering
>
>
>
> to the extent that the activity of the brain can be “read”
>
>
>
> Therein lies the problem with the scans which the research in the video
> used. These scans are not detailed enough to reveal specific thoughts.
> Probes are being developed which have much finer resolutions, so maybe
> there are signals specific enough to get realistic results. But the
> research being reported in the video makes claims beyond the scope of what
> could possibly have been measured. This leaves me very skeptical.
>
>
>
> Let’s see what comes out of research labs that is reproducible
>
>
>
> Yes, let's do that. The research reported in the video is said by the
> researchers to require extensive training on specific individuals, and is
> only reproducible for those individuals, with a success rate of not better
> than 65% (per Blumenstein-- Tang hedges on his success rates). That to me
> is not very impressive for general use applications.
>
>
>
> -- Bob Primak
>
>
>
> On Tuesday, August 27, 2024 at 11:44:25 AM EDT, John P. Rudy <
> jjrudy1 at comcast.net> wrote:
>
>
>
>
>
> Regardless of where the field is today, it seems logical that to the
> extent that the activity of the brain can be “read” that eventually it will
> be understood. Presumably this will occur slowly but eventually happen.
> Who would have believed that “thoughts” can cause an artificial limb to
> move?
>
>
>
> Whether AI can somehow aid in the understanding of a large amount of brain
> data is beyond my understanding, but I’d opt for information from trusted
> sources, not, say, facebook Let’s see what comes out of research labs that
> is reproducible
>
> John
>
> *From:* LCTG <lctg-bounces+jjrudy1=comcast.net at lists.toku.us> *On Behalf
> Of *Harry Forsdick via LCTG
> *Sent:* Tuesday, August 27, 2024 9:40 AM
> *To:* Robert Primak <bobprimak at yahoo.com>
> *Cc:* lctg at lists.toku.us
> *Subject:* Re: [Lex Computer & Tech Group/LCTG] Prompt Engineering
>
>
>
> Bob,
>
>
>
> You are right: I agree with your concern with equating Large Language
> Models (LLMs) with Artificial Intelligence (AI). Doing so succumbs to the
> hype of Wall Street.
>
>
>
> Unfortunately to the uninformed, introducing this TLA into the
> conversation makes the impressive results of LLMs even more mysterious and
> just for techies.
>
>
>
> -- Harry
>
>
>
> On Mon, Aug 26, 2024 at 1:58 PM Robert Primak <bobprimak at yahoo.com> wrote:
>
> Very good finds, Harry.
>
>
>
> Within the context of reading people's thoughts, a lot of what prompt
> engineering can and cannot do depends on the size of the data set it is
> trained on, and the variety of test subjects from whom the training data is
> collected. Too small a sample size in either regard, and there is a real
> chance of researcher bias (conscious or unconscious) entering into the
> picture and affecting the output from the LLM.
>
>
>
> I do not equate LLMs with AI, so I restrict my terms to what we are
> talking about -- LLMS only, not more general AI.
>
>
>
> -- Bob Primak
>
>
>
>
>
> On Monday, August 26, 2024 at 11:35:42 AM EDT, Harry Forsdick via LCTG <
> lctg at lists.toku.us> wrote:
>
>
>
>
>
> Folks,
>
>
>
> Remember when Conor O'Mahony gave his three excellent talks about AI / ML
> systems? [see
> https://docs.google.com/document/d/1fj8FcfD_e-NEi20O3AL_8fg45DdB136fvyCNl7V2gaM/edit?usp=sharing
> ]
>
>
>
> One of the topics he talked about was "prompt engineering".
>
>
>
> I interpreted what was said about prompt engineering to refer to the kinds
> of things we all did with plain old Google to get it to return the kind of
> results we were after.
>
>
>
> I recently asked https://perplexity.ai the question "*What does "prompt
> engineering" mean in the context of AI search systems?*". I learned that
> my interpretation was only partially correct. Instead of being just things
> an end-user does, prompt engineering is also something that a developer of
> an AI question/answering system must do to take the query submitted by
> end-users, and add additional controls to get the AI answer engine to
> return a reasonable, readable answer.
>
>
>
> One of the references in this response,
> https://mitsloanedtech.mit.edu/ai/basics/effective-prompts/, discusses
> what an end user should learn to do. It basically says that this is like
> learning how to ask questions of an expert who knows a lot about the
> subject of your query: you can steer the answer to the one you are after if
> you just ask the question correctly. To quote from the above reference:
>
>
>
> Prompts are your input into the AI system to obtain specific results. In
> other words, prompts are conversation starters: what and how you tell
> something to the AI for it to respond in a way that generates useful
> responses for you. After that, you can build a continuing prompt, and the
> AI will produce another response accordingly. It’s like having a
> conversation with another person, only in this case the conversation is
> text-based, and your interlocutor is AI.
>
>
>
> Below is the answer I got back from Perplexity. If you want to dig deeper
> than the Perplexity answer, there are references to source material used in
> the response.
>
>
>
> Regards,
>
>
>
> -- Harry
>
>
>
>
>
> *What does "prompt engineering" mean in the context of AI search systems?*
>
> Prompt engineering is a crucial process in the context of AI search
> systems, particularly for large language models (LLMs) and generative AI
> tools. It involves crafting well-structured and effective input queries or
> instructions to guide AI models in producing desired outputs or
> responses[1].
>
>
> *Definition and Purpose*
> Prompt engineering refers to the art and science of designing and
> optimizing prompts to elicit specific behaviors from AI models[4]. Its
> primary goal is to bridge the gap between human intention and machine
> understanding, enabling AI systems to generate accurate, relevant, and
> contextually appropriate responses[2].
>
> *Components of Effective Prompts*
>
> 1. *Instruction*: Prompts often require specific and clear requests to
> receive the desired output[3].
>
> 2. *Context*: Providing relevant background information helps the AI
> model understand the task better[3].
>
> 3. *Input Data*: This includes any necessary information for the AI to
> process and generate a response[3].
>
> 4. *Output Format*: Specifying the desired format of the response can
> improve the accuracy and relevance of the AI's output[3].
>
> *Role of Prompt Engineers*
> AI prompt engineers serve as intermediaries between machine learning
> models and human users[3]. Their responsibilities include:
>
> 1. Developing sets of inputs to train models for optimal outputs
> 2. Writing text-based prompts for various tasks (e.g., essay writing, blog
> post generation)
> 3. Evaluating AI systems for idiosyncrasies
> 4. Training and fine-tuning emerging AI tools
>
> *What does "prompt engineering" mean in the context of AI search systems?*
> Prompt engineering plays a vital role in AI search systems by:
>
> 1. *Improving Accuracy*: Well-crafted prompts lead to more precise and
> relevant responses from AI models[4].
> 2. *Enhancing User Experience*: Clear and concise prompts make it easier
> for users to interact effectively with AI models[4].
> 3. *Mitigating Biases*: Careful prompt design helps minimize the risk of
> generating inappropriate or biased content[4].
> 4. *Ensuring Consistency*: Proper prompting techniques enable more
> predictable and reliable AI responses[4].
>
> *Skills Required for Prompt Engineering*
> To excel in prompt engineering, professionals should possess:
>
> 1. Understanding of AI, ML, and Natural Language Processing (NLP)
> 2. Programming skills, particularly in Python
> 3. Strong communication skills
> 4. Knowledge of cognitive psychology and linguistics
> 5. Experience with pre-trained AI models like GPT-3 or GPT-4[3]
>
> In conclusion, prompt engineering is a critical aspect of AI search
> systems, focusing on optimizing the interaction between humans and AI
> models to produce high-quality, relevant, and accurate responses.
>
> Citations:
> [1] https://en.wikipedia.org/wiki/Prompt_engineering
> [2] https://www.datastax.com/guides/what-is-prompt-engineering
> [3]
> https://www.techtarget.com/searchenterpriseai/definition/AI-prompt-engineer
> [4] https://cloud.google.com/discover/what-is-prompt-engineering
> [5] https://www.ibm.com/topics/prompt-engineering
> [6] https://www.akooda.co/blog/what-is-prompt-engineering
> [7] https://researchguides.mvc.edu/ai/prompts
> [8] https://mitsloanedtech.mit.edu/ai/basics/effective-prompts/
>
>
>
> Harry Forsdick <http://www.forsdick.com/resume/>
> Lexington Photo Scanning <http://lexingtonphotoscan.com/>
> Town Meeting Member Precinct 7 <http://lexingtontmma.org/>
> harry at forsdick.com
> <https://mail.google.com/mail/?view=cm&fs=1&tf=1&to=harry@forsdick.com>
> www.forsdick.com
>
>
>
> 46 Burlington St.
> Lexington, MA 02420 <https://goo.gl/xZXT2F>
> (781) 799-6002 (mobile) <callto:17817996002>
>
> Click <http://forsdick.weebly.com/home/my-websites> to see my websites
>
>
>
> *Lafayette Returns*
> 200th Anniversary Reenactment
> *---->* September 2, 2024 (Labor Day) 1pm-2pm
>
> Lexington Battle Green
>
>
> Procession, Lafayette Reenactor, Minute Men, School Children, Bell Ringing,
>
> Period Costumes, 🔥 Cannon Fire 🔥, and ... cookies shaped like Lafayette
>
> ===============================================
> ::The Lexington Computer and Technology Group Mailing List::
> Reply goes to sender only; Reply All to send to list.
> Send to the list: LCTG at lists.toku.us Message archives:
> http://lists.toku.us/pipermail/lctg-toku.us/
> To subscribe: email lctg-subscribe at toku.us To unsubscribe: email
> lctg-unsubscribe at toku.us
> Future and Past meeting information: http://LCTG.toku.us
> List information: http://lists.toku.us/listinfo.cgi/lctg-toku.us
> This message was sent to bobprimak at yahoo.com.
> Set your list options:
> http://lists.toku.us/options.cgi/lctg-toku.us/bobprimak@yahoo.com
>
> ===============================================
> ::The Lexington Computer and Technology Group Mailing List::
> Reply goes to sender only; Reply All to send to list.
> Send to the list: LCTG at lists.toku.us Message archives:
> http://lists.toku.us/pipermail/lctg-toku.us/
> To subscribe: email lctg-subscribe at toku.us To unsubscribe: email
> lctg-unsubscribe at toku.us
> Future and Past meeting information: http://LCTG.toku.us
> List information: http://lists.toku.us/listinfo.cgi/lctg-toku.us
>
> This message was sent to comahony at yahoo.com.
> Set your list options:
> http://lists.toku.us/options.cgi/lctg-toku.us/comahony@yahoo.com
>
> ===============================================
> ::The Lexington Computer and Technology Group Mailing List::
> Reply goes to sender only; Reply All to send to list.
> Send to the list: LCTG at lists.toku.us Message archives:
> http://lists.toku.us/pipermail/lctg-toku.us/
> To subscribe: email lctg-subscribe at toku.us To unsubscribe: email
> lctg-unsubscribe at toku.us
> Future and Past meeting information: http://LCTG.toku.us
> List information: http://lists.toku.us/listinfo.cgi/lctg-toku.us
> This message was sent to tedpkphd at gmail.com.
> Set your list options:
> http://lists.toku.us/options.cgi/lctg-toku.us/tedpkphd@gmail.com
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.toku.us/pipermail/lctg-toku.us/attachments/20240831/98ea866f/attachment.htm>
More information about the LCTG
mailing list