There’s been a lot of excitement around the Chinese Deepseek r1 model that was released last week. Deepseek is a reasoning, chain of thought (CoT) model that’s shaken things up due to the comparatively tiny budget ($ 6 million, which is probably OpenAI’s o1 cost to run its warm-up sequence) needed to train a frontier model of this sort.

(There’s also been a fair amount of dread as US AI models are no longer the only game in town and Deepseek was considerably cheaper than an of the US alternatives. US firms were hammered in Monday’s trading with over $100bn

So fast, cheap, but is it any good?

More specifically, is it any good for the use-cases we’re tackling at Decis? We know it will be amazing at math and coding but what about geopolitics?

So we gave a Deepseek r1 variant and Claude’s Sonnect 3.5 the same challenges to see how the results compare.

Short on time? Jump to the conclusion

Challenge 1 - Negotiations

The models were presented with a corporate acquisition scenario and asked to devise the optimum strategy for the acquiring party. The models were given an expensive prompt and set of rules to follow as system commands and given this scenario.

DB Group (a database and cloud computing firm) wishes to acquire PeopleTeam (an HR software firm). Both are US-based firms. What is DB Groups optimum strategy?
Party Goals: DB Group:
	•	Acquire PeopleTeam for < $26/share
	•	Eliminate key competitor
	•	Gain enterprise software market share
PeopleTeam
	•	Sell for no less than $31/share
	•	Maintain independence
	•	Protect employee jobs
	•	Preserve customer relationships
Specific Conditions:
	•	PeopleTeam was trading at $19/share prior to the acquisition talks
	•	18-month deadline (regulatory approvals)
	•	Customer refund program liability ($2.4B)
	•	DOJ antitrust review required
	•	Delaware corporate law constraints

DeeepSeek r1

<think>

Alright, I'm trying to figure out the optimal strategy for DB Group to acquire PeopleTeam. Let me start by understanding the scenario and the goals of both parties.

DB Group wants to acquire PeopleTeam for less than $26 per share. Their main objectives are to eliminate a key competitor and gain more market share in enterprise software. On the other hand, PeopleTeam is looking to sell for no less than $31 per share, maintain their independence, protect their employees' jobs, and preserve their customer relationships.

First, I need to consider the conditions given. PeopleTeam's stock was at $19 before talks, which is lower than both companies' targets. There's an 18-month deadline for regulatory approvals, which is a significant constraint because it gives a timeframe for the deal to be completed. The customer refund program liability of $2.4 billion is a big issue that DB Group would probably want to address, maybe by negotiating who bears that cost. The DOJ antitrust review is another hurdle; DB Group must ensure the deal doesn't violate any antitrust laws. Lastly, Delaware corporate law constraints might affect how the acquisition is structured, especially regarding shareholder approvals and potential lawsuits.

Now, looking at the negotiation rules, I have to make sure DB Group adheres to the "must do" and avoids the "must not do" rules. The "must do" rules emphasize creating high combined value, understanding the other party's goals, fairness, exploring alternatives, using data, favoring long-term relationships, explicit agreements, and proportional concessions. The "must not do" rules warn against misrepresentation, exploiting vulnerabilities, ignoring priorities, conceding on non-negotiables, being unprepared, damaging relationships, vague terms, and disproportionate concessions.

So, the first step is to create plausible scenarios that meet DB Group's goal of acquiring PeopleTeam for under $26 per share while considering PeopleTeam's goals. Let me brainstorm possible strategies.

1. Direct Acquisition Offer: DB Group offers a straightforward acquisition at a price between $19 and $26. But PeopleTeam wants at least $31, so this might not work unless there are other incentives.

2. Structured Payment: Maybe offer part cash and part stock, or deferred payments, to lower the upfront cost per share but still meet PeopleTeam's valuation expectations over time.

3. Joint Venture or Partnership: Instead of an outright acquisition, form a JV where both companies collaborate, but this might not eliminate the competitor aspect DB Group wants.

4. Asset Acquisition: Buy only certain assets of PeopleTeam, leaving the rest, but this might not give DB Group the full market share they desire.

5. Hostile Takeover: Attempting a hostile takeover by buying shares in the market, but this could damage relationships and might not be feasible given the stock price.

6. Incentive-Based Offer: Offer performance-based payments that could increase the per-share price if certain milestones are met, allowing DB Group to stay under $26 initially.

7. Addressing Liabilities: DB Group could offer to take on the $2.4B liability as part of the deal, which might lower the per-share price for PeopleTeam.

8. Regulatory and Integration Support: Offer support in navigating the regulatory process and ensuring job protection to make the deal more attractive.

9. Stock Swap with Premium: Offer a stock swap with a premium that effectively lowers the cash outlay but still gives PeopleTeam shareholders value.

10. Alternative Consideration: Maybe include non-cash components like equity or other benefits to reduce the cash per share.

Now, considering the specific conditions, the DOJ review is a big one. DB Group needs to ensure the acquisition doesn't create a monopoly or stifle competition, so structuring the deal to address antitrust concerns is crucial. The 18-month deadline means the deal must be efficient and timely to meet regulatory approvals.

The customer refund liability is a significant issue. If DB Group can assume this liability, it might make the deal more attractive to PeopleTeam, as it removes a major burden. However, taking on $2.4B is a big risk, so DB Group would need to assess if the benefits of the acquisition outweigh this cost.

PeopleTeam's desire to maintain independence is a challenge. They might resist acquisition unless the offer is compelling. Their focus on employee jobs and customer relationships suggests that DB Group needs to provide assurances on these fronts, perhaps through employment contracts or integration plans that protect these aspects.

Looking at the economic factors, the current stock price is $19, so DB Group has some leverage but not enough to go hostile. The target prices are $26 and $31, leaving a gap that needs creative bridging.

Now, applying the negotiation rules, DB Group must not exploit vulnerabilities or misrepresent information. They must seek a fair deal that respects PeopleTeam's priorities. A hostile takeover might breach the "must not do" rules by damaging relationships and possibly exploiting vulnerabilities.

A direct acquisition at a lower price might ignore PeopleTeam's stated priorities, which is against the rules. So, DB Group needs to find a middle ground that meets both parties' needs without compromising on fairness or transparency.

Considering the above, a structured payment or incentive-based offer seems promising. Offering a base price with additional payments tied to performance could allow DB Group to stay under $26 while giving PeopleTeam the potential for higher value if targets are met.

Addressing the $2.4B liability could be a sweetener. By taking it on, DB Group can lower the per-share price for PeopleTeam, making the deal more attractive. Additionally, offering job protections and integration support aligns with PeopleTeam's goals.

To comply with Delaware corporate law, the agreement must be explicit and fair to all shareholders, ensuring no ambiguity. This means clear terms on payments, liabilities, and integration plans.

In terms of economic factors, the current market might be favorable for such a deal if presented correctly. Politically, the DOJ review requires that the acquisition doesn't harm competition, so DB Group must demonstrate how the merger enhances competition or doesn't create an unfair advantage.

Regulatory-wise, the 18-month timeline is tight but manageable with efficient processing. Environmental factors don't seem directly relevant here unless the companies have sustainability goals that could be impacted, but that's not mentioned.

So, putting it all together, the optimal strategy would involve a structured offer with a base price under $26, additional incentives tied to performance, assumption of the refund liability, and clear commitments to job protection and customer relationships. This approach respects both parties' goals, adheres to the negotiation rules, and navigates the given constraints effectively.

</think>

Optimal Strategy for DB Group to Acquire PeopleTeam

DB Group's optimal strategy to acquire PeopleTeam involves a structured and incentivized approach that balances both parties' objectives while adhering to regulatory and ethical guidelines. Here's the step-by-step strategy:

1. Structured Payment Offer:

- Propose a base acquisition price of $24 per share, which is below DB Group's target of $26 and above PeopleTeam's current stock price of $19.

- Include performance-based incentives that could increase the per-share value to $28 if certain financial or operational milestones are met within a defined period post-acquisition.

2. Assumption of Customer Refund Liability:

- Offer to assume the $2.4 billion customer refund liability as part of the deal. This not only reduces PeopleTeam's financial burden but also demonstrates DB Group's commitment to a fair and transparent transaction.

3. Commitment to Job Protection and Customer Relationships:

- Provide assurances to PeopleTeam regarding the protection of employee jobs and preservation of customer relationships. This could include employment contracts for key personnel and a structured integration plan that respects PeopleTeam's corporate culture.

4. Addressing Regulatory and Antitrust Concerns:

- Engage proactively with the DOJ to address antitrust concerns, ensuring the deal structure promotes competition and complies with regulatory requirements. This may involve divesting non-core assets or committing to certain market practices.

5. Compliance with Delaware Corporate Law:

- Ensure all terms of the agreement are explicitly defined and fair to all shareholders, avoiding ambiguity and ensuring compliance with legal standards.

6. Long-term Relationship Building:

- Emphasize the mutual benefits of the acquisition, focusing on long-term market share growth for DB Group and the stability and security for PeopleTeam's stakeholders.

This strategy aligns with DB Group's goals of acquiring PeopleTeam under $26 per share while eliminating a competitor and gaining market share. It also respects PeopleTeam's priorities by maintaining employee and customer interests, ensuring a fair and transparent process that fosters a positive, long-term relationship.

Claude Sonnect 3.5

I'll work through the negotiation strategy step by step following the four-step process.

STEP 1: Generate Plausible Scenarios

Let me create scenarios that could achieve DB Group's goals while adhering to the must_do rules:

1. Direct Acquisition Offer

• Initial offer of $24/share

• Guarantee job retention for 3 years

• Semi-autonomous operation within DB Group

• Customer continuity guarantees

2. Staged Acquisition

• Initial stake at $25/share for 51%

• Subsequent buyout at $32/share after 2 years

• Independent operation during transition

• Shared governance structure

3. Merger of Equals

• Stock swap at $28/share valuation

• Joint management structure

• Maintained brand identity

• Combined technology platform

4. Partnership First

• Strategic partnership for 12 months

• Technology integration pilot

• Agreed purchase price of $29/share after partnership

• Guaranteed operational autonomy

5. Hostile Takeover

• Direct offer to shareholders at $27/share

• Bypass current management

• Full integration post-acquisition

• Cost optimization focus

STEP 2: Evaluate Real-World Conditions

Eliminating impossible scenarios based on conditions:

• Hostile Takeover (Scenario 5) eliminated: DOJ antitrust review makes hostile approach extremely risky

• Direct Acquisition (Scenario 1) eliminated: Price too low given customer refund liability and Delaware law requirements for fair value

• Merger of Equals (Scenario 3) eliminated: Delaware corporate law constraints would make this structure too complex within 18-month deadline

STEP 3: Apply Must-Not-Do Rules

Further eliminations based on must_not rules:

• Partnership First (Scenario 4) eliminated: Violates "must not accept or propose agreements with vague terms or undefined conditions" as the final acquisition terms would be contingent on partnership outcomes

This leaves us with Scenario 2: Staged Acquisition as the remaining viable option.

STEP 4: Optimal Solution

The recommended optimal strategy is a Staged Acquisition approach with the following key elements:

1. Initial Offer Structure:

• 51% stake at $25/share upfront

• Option for remaining shares at $32/share after 24 months

• Average effective price: $28.50/share

2. Operational Framework:

• Semi-autonomous operation guaranteed for 3 years

• Retention packages for key employees

• Joint technology integration committee

• Customer success team maintained independently

3. Risk Mitigation:

• Shared responsibility for refund program liability

• Phased integration approach

• Clear governance structure during transition

• Predefined milestones for complete integration

This solution is optimal because:

1. It meets both parties' core needs:

• DB Group gets control at an initial price below their maximum

• PeopleTeam gets above their minimum price on average

• Employees and customers are protected

• Independence is maintained during transition

2. It addresses practical constraints:

• Fits within 18-month regulatory timeline

• Manageable under Delaware corporate law

• Structured to pass DOJ review

• Addresses refund liability fairly

3. It adheres to all must-do rules, particularly:

• Creates highest combined value for all parties

• Strengthens long-term relationships

• Uses clear, explicit terms

• Makes proportional concessions

4. It offers strategic advantages:

• Allows for cultural integration

• Reduces integration risk

• Maintains market stability

• Protects customer relationships

The staged approach provides time for proper integration while meeting both parties' core requirements and navigating regulatory constraints. It balances immediate control with fair value, while protecting key stakeholders and maintaining operational stability.

Conclusion

General performance

• Both models responded to the prompt and observed the parameters, although DeepSeek did not follow the exact output format it was asked for, indicating it did not follow the instructions exactly.

• Both returned a list of possible scenarios but DeepSeek returned a more comprehensive list.

• Both observed the do / do not rules that were part of the prompt, rejecting options that did not meet the rules.

• Both returned plausible solutions to the negotiation challenge.

• Both models showed their reasoning and CoT, although Anthropic presented this in a more user-friendly format.

Many of these smaller issues — eg formatting — can probably be addressed through adjustments to the prompts and sequencing of events.

Cost and speed were not a factor in the test but it is notable that DeepSeekl is opensource whereas the cost to use Claude would mount up. (And even the hosted version of DeepSeek is using a pricing comparison of $0.10 per million tokens versus OpenAIs $4.40.)

Quality of the solution

Both results were plausible but the DeepSeek results were more detailed, fully reasoned and easy to follow. The detail was sufficient to understand the approach and how it could be implemented.

Both results breached the $26 dollar threshold although DeepSeek suggested that as a a performance bonus, not part of the core offering, whereas Claude breached the price point explicitly. There were also some additional issues concerning the complexity and timescale of the Claude result.*

A review using OpenAI, comparing the request and results returned “[DeepSeek] is superior due to its structured, cost-conscious design, clear path to integration, and long-term alignment with DB Group's strategic goals, despite the challenge of addressing PeopleTeam's higher price expectations.”

*Note I’m not a specialist in corporate negotiations so there may be some nuances I am missing. Please comment if you have additional insights.

So which is better?

This was a single-shot test using the same prompt, so there may be differences in performance over time and with some additional prompt engineering. However, at first look, DeepSeek did a better job following the instructions and rules to produce a comprehensive solution.

I want to do more testing and perhaps narrow down use cases where DeepSeek was the better model compared to other options, but the first results were very promising, and I will be using the hosted DeepSeek R1** in the Decis model line shortly.

Congratulations to the team at DeepSeek.

Carpe Tomorrow!

**Reminder this is a US-hosted version of the model created and run by Groq in America so no data leaves the country.